Mercurial > repos > lecorguille > anova

<tool id="abims_anova" name="Anova" version="1.1.4">

    <description>N-way anova. With ou Without interactions</description>

    <requirements>
        <requirement type="package" version="3.1.2">R</requirement>
	<requirement type="package" version="1.1_4">r-batch</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:" level="fatal" />
    </stdio>

    <command interpreter="Rscript">
abims_anova.r file "$input" sampleinfo "$sampleinfo" mode "$mode"
condition "c('$condition_1'
#for $i, $s in enumerate( $conditions )
,'${s.condition}'
#end for
)"
interaction $interaction method $method threshold $threshold selection_method $selection_method sep "$sep" dec "$dec" outputdatapvalue $dataMatrixPValue outputdatafiltered $dataMatrixFiltered
    </command>

    <inputs>
        <param name="input" type="data" label="Data Matrix file" format="tabular" help="Matrix of numeric data with headers." />
        <param name="sampleinfo" type="data" label="Sample Metadata file" format="tabular" help="Tabular file with the data metadata : one sample per line and at least two columns : ids and one condition" />

        <param name="mode" type="select" help="Perform the anova tests on column/row" format="text" optional="true">
            <label>Mode</label>
            <option value="row">row</option>
            <option value="column">column</option>
        </param>

        <param name="condition_1" type="text" label="Condition" value="" help="The column name of the condition. ex: hour or treatment" optional="false" />
        <repeat name="conditions" title="Conditions for N-ways anova">
            <param name="condition" type="text" label="Condition" value="" help="The column name of the condition. ex: hour or treatment" />
        </repeat>

        <param name="interaction" type="boolean" label="Enable interaction response p-values" truevalue="T" falsevalue="F" help="Used if more than 1 conditon. The anova will produse p-value according to the interaction between your condition (ex: condition1:conditions2, condition1:conditions3, condition2:conditions3 and condition1:condition2:conditions3)" />

        <param name="method" type="select" help="Method used to apply a correction on the pvalue because of the number of test" format="text" optional="true">
            <label>PValue adjusted method</label>
            <option value="BH">BH</option>
            <option value="holm">holm</option>
            <option value="bonferroni">bonferroni</option>
            <option value="hochberg">hochberg</option>
            <option value="hommel">hommel</option>
            <option value="BY">BY</option>
            <option value="fdr">fdr</option>
            <option value="none">none</option>
        </param>

        <param name="threshold" type="float" label="Threshold" value="0.01" help="max adjusted p.value accepted" />

        <param name="selection_method" type="select" format="text" help="Intersection: all condition p-value must be under the threshold. Union: at least condition p-value must be under the threshold. ">
            <label>Selection method</label>
            <option value="intersection" selected="true">intersection / strong</option>
            <option value="union">union / weak</option>
        </param>

        <param name="sep" type="select" format="text">
            <label>Separator of columns</label>
            <option value="tabulation">tabulation</option>
            <option value="semicolon">;</option>
            <option value="comma">,</option>
        </param>

        <param name="dec" type="text" label="Decimal separator" value="." help="" />

    </inputs>

    <outputs>
        <data name="dataMatrixPValue" format_source="input" label="${input.name}_anova_pvalue.${input.ext}"/>
        <data name="dataMatrixFiltered" format_source="input" label="${input.name}_anova_filtered.${input.ext}"/>
    </outputs>

    <tests>
        <test>
            <param name="input" value="dataMatrix.tsv"/>
            <param name="sampleinfo" value="sampleMetadata.tsv"/>
            <param name="mode" value="row"/>
            <param name="condition_1" value="age"/>
            <param name="conditions_0|condition" value="gender"/>
            <param name="interaction" value="F"/>
            <param name="method" value="BH"/>
            <param name="threshold" value="0.05"/>
            <param name="selection_method" value="union"/>
            <param name="sep" value="tabulation"/>
            <param name="dev" value="."/>
            <output name="dataMatrixPValue" file="dataMatrix.tsv_anova_pvalue.tabular" />
            <output name="dataMatrixFiltered" file="dataMatrix.tsv_anova_filtered.tabular" />
        </test>
    </tests>

    <help>

.. class:: infomark

**Authors** Gildas Le Corguille  ABiMS - UPMC/CNRS - Station Biologique de Roscoff - gildas.lecorguille|at|sb-roscoff.fr

---------------------------------------------------

=====
Anova
=====

-----------
Description
-----------

Analysis of variance (ANOVA) is used to analyze the differences between group means and their associated procedures,
in which the observed variance in a particular variable is partitioned into components attributable to different sources of variation.


-----------
Input files
-----------

+---------------------------+------------+
| Parameter : num + label   |   Format   |
+===========================+============+
| 1 : Data Matrix file      | Tabular    |
+---------------------------+------------+
| 2 : Sample Metadata file  | Tabular    |
+---------------------------+------------+


------------
Output files
------------


***.anova_pvalue.tabular**

    | A tabular file which represents for each metabolite (row), the value of the intensity in each sample (column) + two columns (aovPValue and aovAdjPValue).

***.anova_filtered.tabular**

    | The tabular file xset.anova_pvalue.tabular containing only the metabolites that have been filtered by aovAdjPValue.


------

.. class:: infomark

The outputs ***.anova_filtered.tabular** or ***.anova_pvalue.tabular** are tabular files. You can continue your analysis using it in the following tools:
    | PCA
    | Hierarchical Clustering


---------------------------------------------------

---------------
Working example
---------------


Input files
-----------

**>A part of an example of Data Matrix file input**


+--------+------------------+----------------+
| Name   | Bur-eH_FSP_12    | Bur-eH_FSP_24  |
+========+==================+================+
|M202T601| 91206595.7559783 |106808979.08546 |
+--------+------------------+----------------+
|M234T851| 27249137.275504  |28824971.3177926|
+--------+------------------+----------------+

**>A part of an example of Sample Metadata file input**


+---------------------------+------------+------------+------------+
| Sample name               |   class    |   time     |   batch    |
+===========================+============+============+============+
| Bur-eH_FSP_12             | Bur-eH     |    12      |     1      |
+---------------------------+------------+------------+------------+
| Bur-eH_FSP_24             | Bur-eH     |    24      |     1      |
+---------------------------+------------+------------+------------+
| Bur-NI_FSP_12             | Bur-NI     |    12      |     2      |
+---------------------------+------------+------------+------------+
| Bur-NI_FSP_24             | Bur-NI     |    24      |     2      |
+---------------------------+------------+------------+------------+

Parameters
----------

    | Mode -> **row**
    | column name of condition -> **class**
    | Separator of columns: -> **tabulation**
    | Decimal separator -> **.**
    | PValue adjusted method -> **BH**
    | Threshold -> **0.001**


Output files
------------

**Part of an example of xset.anova_filtered.tabular:**

.. image:: anova_pvalue.png

**Part of an example of xset.anova_pvalue.tabular:**

.. image:: anova_filtered.png


---------------------------------------------------


---------------------------
Position in workflow4metabo
---------------------------


**Upstream tools**

+---------------------------+----------------------------------------+--------+------------------------+
| Name                      | Output file                            | Format | parameter              |
+===========================+========================================+========+========================+
|xcms.diffreport            |xset.diffreport.data_matrix.tsv         | Tabular| Data table file        |
+---------------------------+----------------------------------------+--------+------------------------+
|CAMERA.annotateDiffreport  |xset.annotatediffreport.data_matrix.tsv | Tabular| Data table file        |
+---------------------------+----------------------------------------+--------+------------------------+
|xcms.xcmsSet               |sample_info.tab                         | Tabular| sample info table file |
+---------------------------+----------------------------------------+--------+------------------------+


**Downstream tools**

+---------------------------+---------------------------------------------------------+--------+
| Name                      | Output file                                             | Format |
+===========================+=========================================================+========+
|PCA                        |xset.anova_pvalue.tabular OR xset.anova_filtered.tabular | Tabular|
+---------------------------+---------------------------------------------------------+--------+
|Hierarchical Clustering    |xset.anova_pvalue.tabular OR xset.anova_filtered.tabular | Tabular|
+---------------------------+---------------------------------------------------------+--------+


**General schema of the metabolomic workflow**

.. image:: anova_workflow.png

    </help>

    <citations>
        <citation>Ronald A. Fisher in the 1930s</citation>
    </citations>

</tool>
author	lecorguille
date	Mon, 04 Apr 2016 08:46:20 -0400
parents	7dacba909bb6
children